Asset Details
Do you wish to reserve the book?
To Fold or Not to Fold: a Necessary and Sufficient Condition on Batch-Normalization Layers Folding
Hey, we have placed the reservation for you!
By the way, why not check out events that you can attend while you pick your title.
Oops! Something went wrong.
Looks like we were not able to place the reservation. Kindly try again later.
Are you sure you want to remove the book from the shelf?
To Fold or Not to Fold: a Necessary and Sufficient Condition on Batch-Normalization Layers Folding
Do you wish to request the book?
To Fold or Not to Fold: a Necessary and Sufficient Condition on Batch-Normalization Layers Folding
Please be aware that the book you have requested cannot be checked out. If you would like to checkout this book, you can reserve another copy
We have requested the book for you!
Your request is successful and it will be processed during the Library working hours. Please check the status of your request in My Requests.
Oops! Something went wrong.
Looks like we were not able to place your request. Kindly try again later.
Paper
To Fold or Not to Fold: a Necessary and Sufficient Condition on Batch-Normalization Layers Folding
2022
Overview
Batch-Normalization (BN) layers have become fundamental components in the evermore complex deep neural network architectures. Such models require acceleration processes for deployment on edge devices. However, BN layers add computation bottlenecks due to the sequential operation processing: thus, a key, yet often overlooked component of the acceleration process is BN layers folding. In this paper, we demonstrate that the current BN folding approaches are suboptimal in terms of how many layers can be removed. We therefore provide a necessary and sufficient condition for BN folding and a corresponding optimal algorithm. The proposed approach systematically outperforms existing baselines and allows to dramatically reduce the inference time of deep neural networks.
Publisher
Cornell University Library, arXiv.org
Subject
